A5101899936- Software Engineering Research
- Topic Modeling
- Natural Language Processing Techniques
- Software Testing and Debugging Techniques
- Software Engineering Techniques and Practices
- Computational Physics and Python Applications
- Metabolomics and Mass Spectrometry Studies
- Scientific Computing and Data Management
- Gene expression and cancer classification
- Machine Learning and Data Classification
- AI in Service Interactions
- Statistical Methods in Clinical Trials
- Open Source Software Innovations
Empresarios Agrupados
2023
European Bioinformatics Institute
2008
University of Bremen
2008
Large language models (LLMs) have recently been applied in software engineering to perform tasks such as translating code between programming languages, generating from natural language, and autocompleting it is being written. When used within development tools, these systems typically treat each model invocation independently all previous invocations, only a specific limited functionality exposed the user interface. This approach interaction misses an opportunity for users more deeply...
Generative models have become adept at producing artifacts such as images, videos, and prose human-like levels of proficiency. New generative techniques, unsupervised neural machine translation (NMT), recently been applied to the task generating source code, translating it from one programming language another. The produced in this way may contain imperfections, compilation or logical errors. We examine extent which software engineers would tolerate imperfections explore ways aid detection...
Generative machine learning models have recently been applied to source code, for use cases including translating code between programming languages, creating documentation from and auto-completing methods. Yet, state-of-the-art often produce that is erroneous or incomplete. In a controlled study with 32 software engineers, we examined whether such imperfect outputs are helpful in the context of Java-to-Python translation. When aided by translation model, participants produced fewer errors...
Abstract Summary: Dasty2 is a highly interactive web client integrating protein sequence annotations from currently more than 40 sources, using the distributed annotation system (DAS). Availability: an open source tool freely available under terms of Apache License 2.0, publicly at http://www.ebi.ac.uk/dasty/ Contact: hhe@ebi.ac.uk
Abstract Background: PhysPK stands as a flexible and robust bio-simulation modeling software designed for analysis of population pharmacokinetics (PK) pharmacodynamics (PD) systems. equips users with standard diagnostic plots pre- post-analysis to delineate PK PD within population-based frameworks. Furthermore, facilitates the establishment mathematical models that elucidate intricate interplay between exposure, safety, efficacy. Methods: Enhancing simulation capabilities necessitates...
The Programmer's Assistant is an experimental prototype development environment that integrates a conversational chat component with code editor. aspect powered by code-fluent large language model. user experience provides for discussion of in the editor as well easy transfer generated to under human supervision.